Wczytanie bibliotek, załadowanie danych

import pandas as pd
import itertools
import plotly.graph_objects as go

data = pd.read_csv('complete.csv')
data.head()

	awardYear	category	categoryFullName	sortOrder	portion	prizeAmount	prizeAmountAdjusted	dateAwarded	prizeStatus	motivation	...	org_founded_country	org_founded_countryNow	org_founded_locationString	ind_or_org	residence_1	residence_2	affiliation_1	affiliation_2	affiliation_3	affiliation_4
0	2001	Economic Sciences	The Sveriges Riksbank Prize in Economic Scienc...	2	1/3	10000000	12295082	2001-10-10	received	for their analyses of markets with asymmetric ...	...	NaN	NaN	NaN	Individual	NaN	NaN	Stanford University, Stanford, CA, USA	NaN	NaN	NaN
1	1975	Physics	The Nobel Prize in Physics	1	1/3	630000	3404179	1975-10-17	received	for the discovery of the connection between co...	...	NaN	NaN	NaN	Individual	NaN	NaN	Niels Bohr Institute, Copenhagen, Denmark	NaN	NaN	NaN
2	2004	Chemistry	The Nobel Prize in Chemistry	1	1/3	10000000	11762861	2004-10-06	received	for the discovery of ubiquitin-mediated protei...	...	NaN	NaN	NaN	Individual	NaN	NaN	Technion - Israel Institute of Technology, Hai...	NaN	NaN	NaN
3	1982	Chemistry	The Nobel Prize in Chemistry	1	1	1150000	3102518	1982-10-18	received	for his development of crystallographic electr...	...	NaN	NaN	NaN	Individual	NaN	NaN	MRC Laboratory of Molecular Biology, Cambridge...	NaN	NaN	NaN
4	1979	Physics	The Nobel Prize in Physics	2	1/3	800000	2988048	1979-10-15	received	for their contributions to the theory of the u...	...	NaN	NaN	NaN	Individual	NaN	NaN	International Centre for Theoretical Physics, ...	Imperial College, London, United Kingdom	NaN	NaN

5 rows × 52 columns

Obróbka danych

awards_in_year = data.groupby(['awardYear', 'category']).size() \
    .to_frame('totalNumberOfAwards') \
    .reset_index()

categories = awards_in_year['category'].unique()

year_min = awards_in_year['awardYear'].min()
year_max = awards_in_year['awardYear'].max()
years = list(range(year_min, year_max+1))

years_categories = itertools.product(years, categories)
new_index = pd.MultiIndex.from_tuples(years_categories, names=['awardYear', 'category'])

awards_in_year = awards_in_year.set_index(['awardYear', 'category']).reindex(new_index)

awards_by_year = awards_in_year.groupby(level=1) \
    .cumsum() \
    .groupby(level=1) \
    .fillna(method='ffill') \
    .fillna(0) \
    .reset_index()

awards_by_year

	awardYear	category	totalNumberOfAwards
0	1901	Chemistry	1.0
1	1901	Literature	1.0
2	1901	Peace	2.0
3	1901	Physics	1.0
4	1901	Physiology or Medicine	1.0
...	...	...	...
709	2019	Literature	116.0
710	2019	Peace	134.0
711	2019	Physics	213.0
712	2019	Physiology or Medicine	219.0
713	2019	Economic Sciences	84.0

714 rows × 3 columns

Przygotowanie animowanego wykresu

awards_by_year['color'] = awards_by_year['category'].map({'Chemistry': '#FD0100',
                                                          'Literature': '#F76915',
                                                          'Peace': '#EEDE04',
                                                          'Physics': '#A0D636',
                                                          'Physiology or Medicine': '#2FA236',
                                                          'Economic Sciences': '#333ED4'
                                                         })

def frames_animation(data, title):
    list_of_frames = []
    min_year = data['awardYear'].min()
    max_year = data['awardYear'].max()

    for year in range(min_year, max_year+1):
            df = data[data['awardYear'] == year]
            df = df.sort_values(by='totalNumberOfAwards', ascending=False)
            list_of_frames.append(go.Frame(data=[go.Bar(x=df['category'],
                                                        y=df['totalNumberOfAwards'],
                                                        marker_color=df['color'],
                                                        hoverinfo='none',
                                                        textposition='outside',
                                                        texttemplate='%{y}',
                                                        cliponaxis=False,
                                                       )
                                                ],
                                           layout=go.Layout(font={'size': 14},
                                                            xaxis={'showline': True, 'visible': True},
                                                            yaxis={'showline': True, 'visible': True},
                                                            bargap=0.15,
                                                            title=go.layout.Title(
                                                                text=f'{title} {year} <br><sup>Sorted in descending order</sup>',
                                                                xref='paper',
                                                                x=0),
                                                           )
                                          )
                                 )
    return list_of_frames 

def bar_race_plot (df, title, list_of_frames):
    min_year = df['awardYear'].min()
    
    initial_df = initial_names = df[df['awardYear'] == min_year]
    initial_names = initial_df['category']
    initial_numbers = initial_df['totalNumberOfAwards']
    initial_color = initial_df['color']
    
    fig = go.Figure(
        data=[go.Bar(x=initial_names,
                     y=initial_numbers,
                     marker_color=initial_color,
                     hoverinfo='none',
                     textposition='outside',
                     texttemplate='%{y}',
                     cliponaxis=False)],
        layout=go.Layout(font={'size': 14},
                         xaxis={'showline': True, 'visible': True},
                         yaxis={'showline': True, 'visible': True,
                                'range': (0, 300)},
                         bargap=0.15,
                         title=go.layout.Title(
                             text=f'{title} {min_year} <br><sup>Sorted in descending order</sup>',
                             xref='paper',
                             x=0),
                         updatemenus=[dict(type="buttons",
                                           buttons=[dict(label="Play",
                                                         method="animate",
                                                         args=[None,
                                                               {"frame": {"duration": 200, "redraw": True},
                                                                "fromcurrent": True}
                                                              ]),
                                                    dict(label="Stop",
                                                         method="animate",
                                                         args=[[None],
                                                               {"frame": {"duration": 0, "redraw": False},
                                                                "mode": "immediate","transition": {"duration": 0}}
                                                              ])
                                                   ])
                                     ]),
        frames=list(list_of_frames))
    
    fig.update_xaxes(tickangle=40)
    
    return fig

title = 'Total Number of Nobel Prize Laureates by Category'
list_of_frames = frames_animation(awards_by_year, title)
fig = bar_race_plot(awards_by_year, title, list_of_frames)
fig.show()